Individual skill

daymade-sector-research

A-share sector research: computes board-wide Top N gainers, cross-checks week/month announcement windows across two sources, and grades market-sentiment evidence (L1–L3), via parallel Agent Team execution with fresh-context adversarial verification. Use for 「XX 行业 Top N/Top 10 标的」, 「这些标的最近一周/一个月发过哪些公告」, 「判断 XX 行业/板块现在的市场情绪」, or 「用 Agent Team 做行业投研」/对抗验证行业研究结论。

daymade-financial/daymade-sector-research/SKILL.md

Read pinned source

Source commit 7c4d326ddd94d504e00e241ba49498e95160afbe

What was checked

Matches the observed repository HEAD: Yes
Scanner rules are current: Yes
Repository scan complete: No
Skill scan complete: No
Observed behavior: Network or broad shell
Last checked: Nov 4, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings): 1,522
Repository last updated: Nov 6, 2026
License: MIT

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

research Derived category

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files

SKILL.mdcore · 8,317 bytes
SKILL.mdcore · 8,317 bytes
references/agent-orchestration.mddoc · 3,080 bytes
references/cninfo-announcements.mddoc · 7,378 bytes
references/gangtise-scout.mddoc · 2,164 bytes
references/market-data.mddoc · 5,357 bytes
references/sentiment-evidence.mddoc · 3,117 bytes
scripts/ann_query.pyruns · 15,436 bytes
scripts/top_n_pipeline.pyruns · 9,264 bytes

Read excerpt


# A股行业投研 Skill

对某个申万行业/东财板块做一次完整投研交付：**Top N 涨幅标的 → 公告窗口检索 → 市场情绪判断 → Agent Team 对抗验证 → 综合报告**。

## 铁律（每次执行都必须遵守，违反代价最高）

1. **宁可标注不确定，不可给错误答案**（用户原话，最高纪律）。没有十足把握的事实写「不确定/未核实」，不编、不猜、不省略来源。推断与观察必须分开表述。
2. **基于证据、基于数据**。每个结论 trace 到一手数据源（API 返回 / CSV 落盘 / 官方公告）；汇报数值时从工具输出原文照抄，禁凭印象转写。
3. **证据分级 L1–L3**：L1 一手行情（交易所/行情接口实时值）；L2 带时间戳的媒体/公告报道；L3 未核实标题或传闻。判断情绪时只允许 L1/L2 承重，L3 只能作为「待核实线索」列出。
4. **0 条双向读**：月窗口公告 0 条 ≠ 真无公告。必须扩宽窗（90 天）+ 第二数据源核对，证明「真无」或发现参数错误，才能下结论。
5. **双源交叉**：公告检索必须巨潮 + 东财两源对照；单一数据源发现的「重要公告」也要在另一源确认存在，不一致必须如实标注。
6. **盘中快照标注漂移**：盘中取的行情数值是瞬时快照会漂移，任何引用必须带快照时间戳，报告里注明「盘中快照」。
7. **数值照抄落盘 CSV**：中间数值必须落盘（脚本输出 CSV / agent 落盘文件），报告引用时照抄 CSV 值，不凭对话记忆。
8. **Agent Team 编排纪律**：见 [references/agent-orchestration.md](references/agent-orchestration.md)——子代理显式 `model:'sonnet'`；SendMessage 交付协议；每条 finding 带可证伪锚点；验证用 fresh-context 对抗性 agent；禁 spawn 重复 agent。